BoltNet:面向边缘设备的超轻量级植物物种识别卷积网络(341K 参数,Pl@ntNet300K F1=0.682)
面向边缘设备的超轻量级植物识别模型，在精度与效率间取得良好平衡，对农业物联网应用有参考价值。
arXiv 8-12 上线论文,作者:Daniel Rossi、Guido Borghi、Roberto Vezzani。论文提出 BoltNet,一种结合 Spatial Redistribution Bottleneck 与 Logit PreSampling 的超轻量级全卷积架构,在 Pl@ntNet300K 上达到 0.682 F1-score(341K 参数,1.37 MB),为评估低于 2 MB 模型中的最高 F1,接近大参数量卷积骨干网络。在 Raspberry Pi 5、Jetson Orin Nano、Hailo-8 上的实测 FPS/W 与 CPU/GPU/NP 应用效率最优。[预印本]
Abstract:Automated plant species identification from citizen-science imagery is an established, demanding fine-grained recognition problem: large taxonomic label spaces, visually similar species, and long-tailed observations require real model capacity, while field use constrains memory, latency, and power. Model size is only part of the deployment cost: intermediate activations held in memory during inference and platformdependent execution behavior matter too, so compact recognition must be assessed on target hardware rather than through complexity metrics alone. We present BoltNet, an ultra-lightweight fully convolutional architecture combining a Spatial Redistribution Bottleneck and Logit PreSampling to improve the tradeoff between predictive performance and model size in high-cardinality classification, and report the AccuracyCompression Tradeoff as a complementary diagnostic. On Pl@ntNet300K, BoltNet reaches 0.682 F1-score with 341K parameters (1.37 MB), the highest F1-score among evaluated models below 2 MB and close to substantially larger convolutional backbones. Model-only measurements on a Raspberry Pi 5, Jetson Orin Nano, and Hailo-8 characterize execution across CPU, GPU, and NPU platforms, where BoltNet is the most consistently efficient model, with the best FPS/W on the GPU and NPU and second-best on the CPU. Results on AIDERv2 and CLRS provide secondary evidence of transfer across environmental image-classification tasks. Code available at: this https URL
Comments:Accepted at the CVPPA (Computer Vision Problems in Plant Phenotyping and Agriculture) workshop, ECCV 2026. 17 pages, 2 figures
Subjects:Computer Vision and Pattern Recognition (cs.CV)
MSC classes:I.4.9, I.2.10, C.3
Cite as:arXiv:2608.11844 [cs.CV]
(or arXiv:2608.11844v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.11844
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Daniel Rossi [view email]
[v1] Wed, 12 Aug 2026 09:34:52 UTC (515 KB)